Exploring the relationship between Diabetes and its Risk Factors using Generalized Additive Models (GAMs)

Christopher Oddom, Denis Folitse, Sandani Kumanayake, Owen Gallagher

2023-05-08

Background of Study

Motivation

Objectives

Methodology

Data

This data is collected from kaggle, updated by Aksha Gattatray Khare with the objective of predicting whether a patient has diabetes, based on certain diagnostic measurements. In total, the data contains 8 variables listed below

Methodology

Descriptive Analysis

Histogram of Original Variables

Descriptive Analysis

Stripplot

Descriptive Analysis | continue

Histogram of Variables

Descriptive Analysis

Boxplot of Variables by Outcome

Descriptive Analysis

Pair Plot

Descriptive Analysis

Correlation Matrix

Model Fit | GAMs splines

Shiny applications not supported in static R Markdown documents

Comparative Study

Partial-Effect Plots

Comparative Study

Tensor Product Plot

Comparative Study

Appraisal

Random Forest Output

Comparative Study

Model Diabetic_Misclass Non_Diabetic_Misclass
GAMs 0.40625 0.0444444
NB 0.21875 0.1777778
RF 0.46875 0.1333333
SGB 0.37500 0.0666667
KNN 0.50000 0.1555556

References